让缺失信息可见，提升智能摘要的决策支持能力
DiSCo: Making Absence Visible in Intelligent Summarization Interfaces
- 基于领域预期对比，识别内容中异常强调或缺失的方面
- 用户研究显示新摘要更详细且助决策，阅读稍难
- 适合需全面了解信息的场景，如旅游住宿选择
智能界面越来越多地使用大语言模型对用户生成内容进行摘要，但这些摘要往往强调提及的内容，忽视缺失的信息。这种存在偏差可能误导依赖摘要做决策的用户。我们提出领域知情对比摘要（DiSCo），一种基于预期的计算方法，通过将每个实体内容与同类住宿中通常讨论的主题参考分布进行对比，识别出相对于领域常态被异常强调或缺失的方面，并将其融入生成文本。在滑雪、海滩和市中心三个住宿领域的用户研究中，DiSCo 摘要被评价为比基线大语言模型摘要更详细、更利于决策，尽管略难阅读。结果表明，建模领域预期可减少存在偏差，提升智能摘要界面的透明度与决策支持能力。
原文摘要 · Abstract (English)
Intelligent interfaces increasingly use large language models to summarize user-generated content, yet these summaries emphasize what is mentioned while overlooking what is missing. This presence bias can mislead users who rely on summaries to make decisions. We present Domain Informed Summarization through Contrast (DiSCo), an expectation-based computational approach that makes absences visible by comparing each entity's content with domain topical expectations captured in reference distributions of aspects typically discussed in comparable accommodations. This comparison identifies aspects that are either unusually emphasized or missing relative to domain norms and integrates them into the generated text. In a user study across three accommodation domains, namely ski, beach, and city center, DiSCo summaries were rated as more detailed and useful for decision making than baseline large language model summaries, although slightly harder to read. The findings show that modeling expectations reduces presence bias and improves both transparency and decision support in intelligent summarization interfaces.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。